正则表达式获取网页<meta name="description" content=内容

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.regex.Matcher;
import java.util.regex.Pattern;


public class Test8 {
    
    static int tempa = 10;
    
    public static void main(String[] args) throws IOException  {
        File file = new File("D:/2cd99ecc9a3b8f2f233cb6d9c17a86b9.jsp");
        String htmlReport = readFileAsString(file);
        //System.out.println(htmlReport);
        //String pattern = "<meta name=\"description\" content=\"(.+?)\r\n(.+?)/>";
        String pattern = "name=\"description\" content=\"(.+?)/>";
        
        Pattern p = Pattern.compile(pattern,Pattern.CASE_INSENSITIVE | Pattern.DOTALL);   
        Matcher matcher = p.matcher(htmlReport);
        

        while (matcher.find()) {
            String tmp = matcher.group(1);
            System.out.println(tmp);
            }
        }
    
    private static String readFileAsString(File file) throws IOException {
        
        StringBuffer strBuff = new StringBuffer();
        String charsetName = "utf-8";
        
        if(file != null && file.exists()){
            
            //InputStream in = new FileInputStream(file);
            InputStreamReader inputStreamReader = new InputStreamReader(new FileInputStream(file), charsetName);
            BufferedReader bufferedReader = new BufferedReader(inputStreamReader);
            String line = null;
            while((line = bufferedReader.readLine()) != null){
                strBuff.append(line);
                strBuff.append("\n");
            }
            
            inputStreamReader.close();
            bufferedReader.close();
            
        } else {
        }
        
        return strBuff.toString();
        
        /*char[] chr = new char[4096];
        final StringBuffer buffer = new StringBuffer();
        final FileReader reader = new FileReader(file);
        try {
            while ((len = reader.read(chr)) > 0) {
                buffer.append(chr, 0, len);
                System.out.println("len=======" + len);
            }
        } finally {
            reader.close();
        }*/
  
    }

}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值